Earticle

This project related to develop and implementation of autonomous vision based mobile robot following human. Human tracking algorithm will be developed to allow a mobile robot to follow a human. A wireless camera will be used for image capturing, and Matlab will be use to process the image captured, followed by controlling the mobile robot to follow the human. This system will allow the robot to differentiate a human in a picture. The foreground and background will be separated and the foreground is used to determine the object whether it’s human or not. Then classification algorithm is applied to find the centroid of the human. This centroid is then compared with the center of the image to get the location of the human with respect to the camera, either at the left or right of the camera. If the human is not in the center of the camera view, then corrective measures is taken so that the human will be in the center of the camera view. Data for the centroid of human is shown through the Graphical User Interface (GUI).

Video tracking is one of the most active research topics recently. Tracking of objects and humans has a very wide set of applications such as teleconferencing, surveillance, and security. We propose a new tracker to enhance the tracking process by making use of SURF descriptor and Particle filter. SURF is one of the fastest descriptors which generates a set of interesting points which are invariant to various image deformations (scaling, rotation, illumination) and robust against occlusion conditions during tracking. Particle filter is one of the commonly used methods in video tracking to solve non-linear and non-Gaussian problems. Particle filter generates a random set of points called particles or samples for any target to be used for tracking through the process of the algorithm. But the fact that the initial particles are chosen randomly causes degradation in efficiency and reliability of the tracking process. It is possible to lose the tracked target at any frame if any change happened in the scene. Previous researches proposed an integration of Particle algorithm and scale invariant feature transform (SIFT) descriptor to overcome potential problems. SIFT is a predecessor of SURF and shares the same characteristics except that SURF is much faster. A comparative study was held between the traditional particle filter, SIFT-Particle tracker and the proposed tracker. The proposed SURF-Particle tracker proved to be more efficient, reliable and accurate than traditional particle filter and SIFT-Particle tracker. The idea of the proposed tracker is to use the discriminative interest points generated by the SURF descriptor as the initial particles/ samples to be fed into particle filter instead of choosing these particles randomly as done in traditional simple particle filter. Experimental results using the Actions as Space-Time Shapes Dataset of the Weizmann Institute of Science proved the correctness of the proposed idea and showed improved efficiency and accuracy resulted from using our proposed tracker over traditional simple particle filter and SIFT-Particle tracker. It also proved to be faster than SIFT-Particle.

This paper provides a comprehensive overview of UAV classification, tracking, and detection, offering researchers a clear understanding of these fundamental concepts. It elucidates how classification categorizes UAVs based on attributes, how tracking monitors real-time positions, and how detection identifies UAV presence. The interconnectedness of these aspects is highlighted, with detection enhancing tracking and classification aiding in anomaly identification. Moreover, the paper emphasizes the relevance of simulations in the context of drones and UAVs, underscoring their pivotal role in training, testing, and research. By succinctly presenting these core concepts and their practical implications, the paper equips researchers with a solid foundation to comprehend and explore the complexities of UAV operations and the role of simulations in advancing this dynamic field.

Object tracking is a common task in computer vision, an essential part of various vision-based applications. After several years of development, object tracking in video is still a challenging problem because of various visual properties of objects and surrounding environment. Particle filter is a well-known technique among common approaches, has been proven its effectiveness in dealing with difficulties in object tracking. However, particle filter is a high-complexity algorithms, which is an severe disadvantage because object tracking algorithms are required to run in real time. In this research, we utilize parallel programming to accelerate particle filter-based object tracking algorithms. Experimental results showed that our approach reduced the execution time significantly.

A novel control algorithm, namely subsection adaptive hill climbing method (SSAHC), for seeking the maximum power point (MPP) of a photovoltaic (PV) panel for any temperature and solar radiation level is proposed. The algorithm is thus a combination of the subsection and adaptive hill climbing methods. In this algorithm, the characteristic curve of power-voltage of PV panel was divided into three subsections, namely large step approximation section, adaptive hill climbing section and maximum power section. Using this method, the MPP tracker (MPPT) can tune adaptively the step to track the MPP of PV system. The main advantage of the MPPT controlled by this new algorithm, when is compared with others, is that it can draw more power at a certain weather condition, especially, in case solar radiation changes rapidly at higher radiation.

This paper presents a study involving prediction of a complicated maneuvering target, with the aim of improving the tracking performance of a fire control system (FCS). In this study, we predict the position of a complicated maneuvering target 5 s in advance using the information up to the current time. Because of the large error caused by the complicated maneuvers and the long prediction time interval, the mechanical system of the fire control system will take a heavy load. In order to cope with this problem, several approaches to decreasing the prediction error have been proposed including the prediction algorithms based on the multiple model(MM) filter, interacting multiple model (IMM) filter, and variable dimension with input estimation (VDIE) filter. Finally, comparative simulation results are presented to verify the performance of the filters.

This paper studies the problem of tracking a re-entry vehicle (RV) in order to predict its impact point on the ground. Re-entry target dynamics combined with super-high speed has a complex non-linearity due to ballistic coefficient variations. However, it is difficult to construct a database for the ballistic coefficient of a unknown vehicle for a wide range of variations, thus the reliability of target tracking performance cannot be guaranteed if accurate ballistic coefficient estimation is not achieved. Various techniques for ballistic coefficient estimation have been previously proposed, but limitations exist for the estimation of non-linear parts accurately without obtaining prior information. In this paper we propose the ballistic coefficient ${\beta}$ model-based interacting multiple model-extended Kalman filter (${\beta}$-IMM-EKF) for precise tracking of an RV. To evaluate the performance, other ballistic coefficient model based filters, which are gamma augmented filter, gamma bootstrapped filter were compared and assessed with the proposed ${\beta}$-IMM-EKF for precise tracking of an RV.

In this paper, a new stereo 3D moving-target tracking system using the MSE (mean square error) and BPEJTC (binary phase extraction joint transform correlator) algorithms is proposed. A moving target is extracted from the sequential input stereo image by applying a region-based MSE algorithm following which, the location coordinates of a moving target in each frame are obtained through correlation between the extracted target image and the input stereo image by using the BPEJTC algorithm. Through several experiments performed with 20 frames of the stereo image pair with $640{\times}480$ pixels, we confirmed that the proposed system is capable of tracking a moving target at a relatively low error ratio of 1.29 % on average at real time.

본 논문은 연안 군사시설 및 주요 기반시설에 대한 침투세력을 감시하는 수영자 탐지 소나에서의 자동 표적추적 알고리즘을 다루었다. 이를 위해 수영자 탐지 소나에서의 해상실험 데이터를 분석하였고, 클러터 환경에서 자동표적 추적을 위한 트랙평가수단으로서 트랙존재확률 기반의 알고리즘을 적용하여 시스템을 구성하였다. 특히 트랙초기화, 확정, 제거, 합병 등의 트랙관리 알고리즘과 단일표적추적 IPDAF(Integrated Probabilistic Data Association Filter), 다중표적추적 LMIPDAF(Linear Multi-target Integrated Probabilistic Data Association Filter) 등의 표적추적 알고리즘을 제시하였으며, 해상실험 데이터 및 몬테카를로 모의실험 데이터를 이용하여 성능을 분석하였다.

In this paper, we discussed automatic target tracking algorithms for diver detection sonar that observes penetration forces of coastal military installations and major infrastructures. First of all, we analyzed sea trial data in diver detection sonar and composed automatic target tracking algorithms based on track existence probability as track quality measure in clutter environment. In particular, these are presented track management algorithms which include track initiation, confirmation, termination, merging and target tracking algorithms which include single target tracking IPDAF (Integrated Probabilistic Data Association Filter) and multitarget tracking LMIPDAF (Linear Multi-target Integrated Probabilistic Data Association Filter). And we analyzed performances of automatic target tracking algorithms using sea trial data and monte carlo simulation data.

This paper presents stable kinematic modeling and path planning and path tracking algorithms for the poisition control of 4-wheeled 2-d.o.f(degree of freedom) mobile robot. We drived the actuated inverse and sensed forward solution for the calculation of actuator velocity and robot velocities. the deal-reckoning algorithm is introduced to calculate the position of WMR in real time. The gaussian functions are applied to control and to design the smooth orientation angle of WMR and the path planning algorithm for obstacle avoidance is prosed. We composed feedback control system to compensate for error because of uncertainty kinematic modeling and measurement noise. The simulation resutls show that the proposed kinematkc modeling and path planning and feedback control algorithms are useful.

본 논문에서는 기존의 MPPT 기법인 Perturbation-and-Observation(이하 P&O)와 modified incremental conductance(이하 modified InCond)에 대해 Matlab과 PSIM의 인터페이스를 통해 일사량 급변시의 동작을 살펴본다. 기존의 논문에서는 각각의 일사량에 대해 효율 면에서 P&O가 InCond에 비해 높지만 일사량 급변시 과도상태에서는 InCond가 더 효율적으로 발표되었다. 이를 검토해 보기 위해 우선 실제 시판되는 태양전지 모듈에 대해 Matlab을 이용한 모델링을 실시함으로써 보다 정확한 값을 얻는다. 다음으로 PSIM을 이용하여 전력변환부와 제어기를 모델링하고 Matlab의 Simulink를 통해 인터페이스를 실시한다. 마지막으로 일사량 급변 시 과도상태와 급변 후에 MPPT 동작을 살펴본다.

As the maximum power operating point (MPOP) of photovoltaic (PV) power systems changes with changing atmospheric conditions, the efficiency of maximum power point tracking (MPPT) is important in PV power systems. Many MPPT techniques have been considered in the past, but techniques using microprocessors with appropriate MPPT algorithms are favored because of their flexibility and compatibility with different PV arrays. Although the efficiency of these MPPT algorithms is usually high, it drops noticeably in case of rapidly changing atmospheric conditions. In this paper, we proposed a new MPPT control method called improved perturb and observe method (ImP&O), anda simple voltage and current characteristic equation of a PV array for PV array simulator. Experimental results verify the accuracy and excellent performance of the proposed MPPT method. ImP&O algorithm is very simple, and has successful tracked the MPOP, even in case of rapidly changing atmospheric conditions.

본 논문에서 4-구륜 2-자유도 이동 로보트의 체계적인 동적 모델링과 경로설계 및 추적 알고리즘을 제안한다. 실시간에서 이동 로보트의 위치 측정을 위해 관성측정장치중의 3가지 요소를 이용한다. 이러한 장치들은 지구의 회전속도 및 중력가속도 등의 여러 요인으로 인해 초기 오차를 가진다. 그래서 초기오차 모델을 유도하고, 실제 데이터와 유도된 모델의 추정 데이터의 확률적 특성을 분석 ${\cdot}$ 비교하여 적합도를 판정하여 사용한다. 관성측정장치의 동작특성은 오차모델과 칼만 필터와 연계된 경우와 배제된 일반적인 경우와 비교한다. 모의실험 결과들은 제안된 경로설계 및 추적 알고리즘이 기존의 방식과 비교하여 보다 유용함을 입증한다.

In this paper, we propose the dynamic modeling, path planning and tracking algorithms of 4-wheeled 2-d.o.f.(degree of freedom) mobile robot(WMR). The gaussian functions are applied to design the smooth path of WMR. To calculate the WMR position in real time, we use three components of inertial measurement units(IMU). These units have initial error because of the rotation rate of earth, gravity acceleration and so on. Therefore we derive the initial error model of IMU, and compare the fitness diagnosis about probability characteristics of real data adn estimated data. The performance of IMU with error model and Kalman filter is compared to that without filter and error model. The simulation results show that the proposed dynamic model, path planning and tracking algorithms are more useful than the conventional control algorithm.

최근 제조업에서의 디지털 전환이 가속화되고 있다. 이에 따라 사물인터넷(internet of things: IoT) 기반으로 현장 데이터를 수집하는 기술의 중요성이 증대되고 있다. 이러한 접근법들은 주로 각종 센서와 통신 기술을 활용하여 특정 제조 데이터를 확보하는 것에 초점을 맞춘다. 현장 데이터 수집의 채널을 확장하기 위해 본 연구는 비전(vision) 인공지능 기반으로 제조 데이터를 자동 수집하는 방법을 제안한다. 이는 실시간 영상 정보를 객체 탐지 및 추적 기술로 분석하고, 필요한 제조 데이터를 확보하는 것이다. 연구진은 객체 탐지 및 추적 알고리즘으로 YOLO(You Only Look Once)와 딥소트(DeepSORT)를 적용하여 프레임별 객체의 움직임 정보를 수집한다. 이후, 움직임 정보는 후보정을 통해 두 가지 제조 데이터(생산 실적, 생산 시간)로 변환된다. 딥러닝을 위한 학습 데이터를 확보하기 위해 동적으로 움직이는 공장 모형이 제작되었다. 또한, 실시간 영상 정보가 제조 데이터로 자동 변환되어 데이터베이스에 저장되는 상황을 재현하기 위해 운영 시나리오를 수립하였다. 운영 시나리오는 6개의 설비로 구성된 흐름 생산 공정(flow-shop)을 가정한다. 운영 시나리오에 따른 제조 데이터를 수집한 결과 96.3%의 정확도를 보였다.

Recently, digital transformation in manufacturing has been accelerating. It results in that the data collection technologies from the shop-floor is becoming important. These approaches focus primarily on obtaining specific manufacturing data using various sensors and communication technologies. In order to expand the channel of field data collection, this study proposes a method to automatically collect manufacturing data based on vision-based artificial intelligence. This is to analyze real-time image information with the object detection and tracking technologies and to obtain manufacturing data. The research team collects object motion information for each frame by applying YOLO (You Only Look Once) and DeepSORT as object detection and tracking algorithms. Thereafter, the motion information is converted into two pieces of manufacturing data (production performance and time) through post-processing. A dynamically moving factory model is created to obtain training data for deep learning. In addition, operating scenarios are proposed to reproduce the shop-floor situation in the real world. The operating scenario assumes a flow-shop consisting of six facilities. As a result of collecting manufacturing data according to the operating scenarios, the accuracy was 96.3%.

An effect ive filter algorithm that can manage radar beam pointing efficiently is needed to track multi-target in the air. For effective beam management the filter has lobe good enough to predict future position of target and based on this filter output radar beam is control led to point toward the predicted target position in the air. In this paper, we investigate the ${\alpha}$-${\beta}$ filter known for its brief filter structure with the steady-state Kalman filter gain, the ruv filter, and the coordinate-transformed filter that can decouple the measurement noise variance.

In this study, constant power generation (CPG) algorithms are introduced for whole range power point tracking in photovoltaic systems. Currently, maximum power point tracking (MPPT) algorithm is widely used for high-power photovoltaic systems. However, MPPT algorithm cannot flexibly control such systems according to changing grid conditions. Maintaining grid stability has become important as the capacity of grid-connected photovoltaic systems is increased. CPG algorithms are required to generate the desired power depending on grid conditions. A grid-connected photovoltaic system is configured, and CPG algorithms are implemented. The performances of the implemented algorithms are compared and analyzed by experimental results.

The Gas Metal Arc(GMA) welding, called Metal Inert Gas(MIG) welding, has been an important component in manufacturing industries. A key technology for robotic welding processes is seam tracking system, which is critical to improve the welding quality and welding capacities. The objectives of this study were to develop the intelligent and cost-effective algorithms for image processing in GMA welding which based on the laser vision sensor. Welding images were captured from the CCD camera and then processed by the proposed algorithm to track the weld joint location. The proposed algorithms that commonly used at the present stage were verified and compared to obtain the optimal one for each step in image processing. Finally, validity of the proposed algorithms was examined by using weld seam images obtained with different welding environments for image processing. The results proved that the proposed algorithm was quite excellent in getting rid of the variable noises to extract the feature points and centerline for seam tracking in GMA welding and could be employed for general industrial application.

The Gas Metal Arc(GMA) welding, called Metal Inert Gas(MIG) welding, has been an important componentin manufacturing industries. A key technology for robotic welding processes is seam tracking system, whichis critical to improve the welding quality and welding capacities. The objectives of this study were to developthe intelligent and cost-effective algorithms for image processing in GMA welding which based on the laservision sensor. Welding images were captured from the CCD camera and then processed by the proposed algorithmto track the weld joint location. The proposed algorithms that commonly used at the present stage were verifiedand compared to obtain the optimal one for each step in image processing. Finally, validity of the proposedalgorithms was examined by using weld seam images obtained with different welding environments for imageprocessing. The results proved that the proposed algorithm was quite excellent in getting rid of the variablenoises to extract the feature points and centerline for seam tracking in GMA welding and could be employedfor general industrial application.